{"id":"https://openalex.org/W3139450269","doi":"https://doi.org/10.1109/imcom51814.2021.9377411","title":"EnvBERT: Multi-Label Text Classification for Imbalanced, Noisy Environmental News Data","display_name":"EnvBERT: Multi-Label Text Classification for Imbalanced, Noisy Environmental News Data","publication_year":2021,"publication_date":"2021-01-04","ids":{"openalex":"https://openalex.org/W3139450269","doi":"https://doi.org/10.1109/imcom51814.2021.9377411","mag":"3139450269"},"language":"en","primary_location":{"id":"doi:10.1109/imcom51814.2021.9377411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/imcom51814.2021.9377411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100607748","display_name":"Dohyung Kim","orcid":"https://orcid.org/0000-0002-6364-1505"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Dohyung Kim","raw_affiliation_strings":["College of Software, Sungkyunkwan University, Suwon, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"College of Software, Sungkyunkwan University, Suwon, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030749036","display_name":"Jahwan Koo","orcid":"https://orcid.org/0000-0002-2844-3183"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jahwan Koo","raw_affiliation_strings":["College of Software, Sungkyunkwan University, Suwon, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"College of Software, Sungkyunkwan University, Suwon, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068522348","display_name":"Ung-Mo Kim","orcid":"https://orcid.org/0000-0001-5464-6358"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ung-Mo Kim","raw_affiliation_strings":["College of Software, Sungkyunkwan University, Suwon, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"College of Software, Sungkyunkwan University, Suwon, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100607748"],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77317289,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"36","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.9047051668167114},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.7679694890975952},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7513728141784668},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.6415677666664124},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5914114713668823},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5165018439292908},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4947804808616638},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4475998878479004},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.42446279525756836},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40585458278656006},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3648177981376648}],"concepts":[{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.9047051668167114},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.7679694890975952},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7513728141784668},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.6415677666664124},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5914114713668823},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5165018439292908},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4947804808616638},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4475998878479004},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.42446279525756836},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40585458278656006},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3648177981376648},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/imcom51814.2021.9377411","is_oa":false,"landing_page_url":"https://doi.org/10.1109/imcom51814.2021.9377411","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 15th International Conference on Ubiquitous Information Management and Communication (IMCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1183586829","display_name":null,"funder_award_id":"NRF-20 18R1D1A1B07049464","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W66588809","https://openalex.org/W746832161","https://openalex.org/W1899504021","https://openalex.org/W1978394996","https://openalex.org/W2054929278","https://openalex.org/W2127626360","https://openalex.org/W2128965734","https://openalex.org/W2131571251","https://openalex.org/W2146241755","https://openalex.org/W2148143831","https://openalex.org/W2250539671","https://openalex.org/W2322938983","https://openalex.org/W2896457183","https://openalex.org/W2900758626","https://openalex.org/W2911489562","https://openalex.org/W2963341956","https://openalex.org/W2963403868","https://openalex.org/W2964548917","https://openalex.org/W2970597249","https://openalex.org/W4385245566","https://openalex.org/W6621912290","https://openalex.org/W6700418084","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6763701032","https://openalex.org/W6766008988"],"related_works":["https://openalex.org/W1592804209","https://openalex.org/W4237698281","https://openalex.org/W4386210978","https://openalex.org/W2772832743","https://openalex.org/W4283808318","https://openalex.org/W3116576821","https://openalex.org/W2943022475","https://openalex.org/W3216120081","https://openalex.org/W3139450269","https://openalex.org/W4313397532"],"abstract_inverted_index":{"Imbalanced":[0],"and":[1,61,98,125],"noisy":[2,68,126],"classification":[3,20,41,48,60,116],"problems":[4,39],"pose":[5],"a":[6,45,102,109],"challenge":[7],"for":[8,19,33,66,105],"predictive":[9,64],"modeling":[10],"as":[11],"most":[12],"of":[13,26,30,95],"the":[14,24,76,86,92,123],"machine":[15],"learning":[16],"algorithms":[17],"used":[18,85],"were":[21],"designed":[22],"around":[23],"assumption":[25],"an":[27],"equal":[28],"number":[29],"non-noisy":[31],"examples":[32],"each":[34],"class.":[35],"Models":[36],"with":[37,80],"these":[38],"cause":[40],"errors.":[42],"We":[43,84],"propose":[44],"multi-label":[46,56,96],"text":[47,59,82],"model":[49,78],"based":[50,74],"on":[51,75,122],"BERT,":[52],"EnvBERT,":[53],"which":[54],"includes":[55],"features":[57],"in":[58],"has":[62],"good":[63],"performance":[65,117],"imbalanced,":[67],"environmental":[69,127],"news":[70,128],"data.":[71,83,129],"EnvBERT":[72,114],"is":[73],"KoBERT":[77],"pre-trained":[79],"Korean":[81],"data":[87,97],"oversampling":[88],"technique":[89],"to":[90],"resolve":[91],"imbalanced":[93,124],"characteristics":[94],"fine-tuned":[99],"while":[100],"setting":[101],"global":[103],"threshold":[104],"label":[106],"prediction.":[107],"As":[108],"result,":[110],"we":[111],"show":[112],"that":[113],"improves":[115],"by":[118],"more":[119],"than":[120],"80%":[121]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}